论文标题
立体声差异的Wasserstein距离
Wasserstein Distances for Stereo Disparity Estimation
论文作者
论文摘要
现有的深度或差异估计方法输出一组预定义的离散值的分布。当真实的深度或差异与这些值中的任何一个不匹配时，这会导致结果不准确。通常通过回归损失间接地学习这种分布的事实会导致对象边界周围歧义区域的进一步问题。我们使用能够输出任意深度值的新神经网络体系结构解决这些问题，以及从真实分布和预测分布之间的Wasserstein距离得出的新损失函数。我们验证了各种任务的方法，包括立体声差异和深度估计以及下游3D对象检测。我们的方法大大减少了模棱两可的区域的错误，尤其是围绕物体边界，极大地影响了对象在3D中的定位，从而实现了3D对象检测中最新的自动驾驶驾驶中的最先进。我们的代码将在https://github.com/div99/w-stereo-disp上找到。
Existing approaches to depth or disparity estimation output a distribution over a set of pre-defined discrete values. This leads to inaccurate results when the true depth or disparity does not match any of these values. The fact that this distribution is usually learned indirectly through a regression loss causes further problems in ambiguous regions around object boundaries. We address these issues using a new neural network architecture that is capable of outputting arbitrary depth values, and a new loss function that is derived from the Wasserstein distance between the true and the predicted distributions. We validate our approach on a variety of tasks, including stereo disparity and depth estimation, and the downstream 3D object detection. Our approach drastically reduces the error in ambiguous regions, especially around object boundaries that greatly affect the localization of objects in 3D, achieving the state-of-the-art in 3D object detection for autonomous driving. Our code will be available at https://github.com/Div99/W-Stereo-Disp.
